Today's tools treat Tiv as an afterthought by flattening its tones, guessing at meaning, with no voice and no real-world products. Kwaghfan is building an open, community-sourced foundation for Tiv AI, and the applied tools that put it to work.
A handful of tools can now translate Tiv text. But they treat the language as a low-resource afterthought, flattening the tonal distinctions that change meaning, and hallucinating on anything legal, medical, or official. They're unreliable exactly where accuracy matters most.
There is no reliable voice. Speech recognition and text-to-speech for Tiv remain perpetually "coming soon," because the phonetic data needed to build them doesn't exist yet.
And where good data does exist, it's locked away as proprietary corpora built to be sold, not shared. Nobody has built the applied products either.
Kwaghfan is building Tiv AI from the ground up, open where others are closed, voice-capable where others stop at text, and deployed where others ship only an API.
A community-sourced dataset built from inside Tiv-speaking communities, covering dialectal variation and real conversational registers. Openly licensed and built to be shared, not sold.
Beyond text: tonal-aware speech recognition and synthesis. Built to sound authentically human, not robotic.
A free public chatbot plus tools for health, agriculture, and government. Not just an API but products people in Benue actually use, in the language they think in.
Maternal health guidance, vaccination schedules, disease outbreak alerts, malaria prevention delivered in Tiv to the populations who need it most. When health information is only in English, rural communities are left behind. Kwaghfan bridges that gap.
Planting calendars, pest management, subsidy information, and best practices reaching farmers in the language they think in, not the language of bureaucracy.
Voter education, civil registration guidance, policy communication, and public announcements making government accessible to every citizen, not just English speakers.
Supporting Tiv-language education, enabling students to access learning materials in their mother tongue, and preserving the language in the digital age.
International development organizations serving Benue State such as WHO, UNICEF, USAID-funded programs, get a communication layer that actually reaches their target populations.
Our chatbot uses a bridge architecture that combines a purpose-built Tiv language model with large-scale AI reasoning by delivering reliability without requiring massive compute. Voice comes next, layered on the same foundation.
A Tiv speaker types or speaks their question in natural Tiv through the chat interface.
Our fine-tuned model converts the Tiv input to English and extracts the user's intent.
A large language model processes the query with domain-specific knowledge bases for accurate answers.
The answer is translated back to natural Tiv and delivered to the user fluent, accurate, instant.
Training data collected through the Kwaghfan community competition. Real Tiv text written by real Tiv speakers, covering health, agriculture, commerce, and daily life.
Built on open-source multilingual models fine-tuned with parameter-efficient methods. No proprietary lock-in, deployable on modest hardware.
Built for open release and grant funding from day one verified by native speakers, documented to research standards, and licensed to be shared. A public good, not a walled garden.
Kwaghfan is designed as an open platform for organizations that need to communicate with Tiv-speaking populations. We work with government, NGOs, healthcare providers, and development organizations.
Custom knowledge bases for your programs. Analytics on citizen engagement. API integration with your existing communication channels.
Reach the populations your programs are designed to serve. Deploy health, education, and agricultural information in the language people actually speak.
Access the first Tiv language corpus for linguistic research. Collaborate on expanding NLP resources for African languages.
Tiv translation API for your applications. License our language data for multilingual model training. Integrate Tiv support into your products.
Whether you're a government agency seeking to reach Tiv speakers, an NGO deploying programs in Benue State, a researcher interested in low-resource NLP, or an investor in African AI infrastructure, we'd like to hear from you.